Related papers: From Flat-Optics Concept to Qualified Hardware: Sk…
Selective classifiers improve model reliability by abstaining on inputs the model deems uncertain. However, few practical approaches achieve the gold-standard performance of a perfect-ordering oracle that accepts examples exactly in order…
Testing software is often costly due to the need of mass-producing test cases and providing a test oracle for it. This is often referred to as the oracle problem. One method that has been proposed in order to alleviate the oracle problem is…
During the design phase of products and before going into production, it is necessary to verify the presence of mechanical plays, tolerances, and encumbrances on production mockups. This work introduces a multi-modal system that allows…
Out of the many deep reinforcement learning approaches for autonomous driving, only few make use of the options (or skills) framework. That is surprising, as this framework is naturally suited for hierarchical control applications in…
Designing systems is typically uncertain and ambiguous at early stages. Set-based design supports alternative exploration and gradual uncertainty reduction during the early lifecycle, making it practical for complex systems design. In…
Real-world image matting is essential for applications in content creation and augmented reality. However, it remains challenging due to the complex nature of scenes and the scarcity of high-quality datasets. To address these limitations,…
Active optical metasurfaces are rapidly emerging as a major frontier in photonics research, development, and commercialization. They promise compact, light-weight, and energy-efficient reconfigurable optical systems with unprecedented…
Understanding what objects could furnish for humans-namely, learning object affordance-is the crux to bridge perception and action. In the vision community, prior work primarily focuses on learning object affordance with dense (e.g., at a…
Optical manipulation techniques offer exceptional contactless control but are fundamentally limited in their ability to perform parallel multitasking. To achieve high-density, versatile manipulation with subwavelength photonic devices, it…
Security and ethics are both core to ensuring that a machine learning system can be trusted. In production machine learning, there is generally a hand-off from those who build a model to those who deploy a model. In this hand-off, the…
Current methods for fabricating lenses rely on mechanical processing of the lens or mold, such as grinding, machining, and polishing. The complexity of these fabrication processes and the required specialized equipment prohibit rapid…
Modern image editing models produce realistic results but struggle with abstract, multi step instructions (e.g., ``make this advertisement more vegetarian-friendly''). Prior agent based methods decompose such tasks but rely on handcrafted…
Offline Handwritten Signature verification presents a challenging Pattern Recognition problem, where only knowledge of the positive class is available for training. While classifiers have access to a few genuine signatures for training,…
Federated Learning (FL) enables the utilization of vast, previously inaccessible data sources. At the same time, pre-trained Language Models (LMs) have taken the world by storm and for good reason. They exhibit remarkable emergent abilities…
While text-to-image models have made strong progress in visual fidelity, faithfully realizing complex visual intents remains challenging because many requirements must be tracked across grounding, generation, and verification. We refer to…
Atomic systems have long provided a useful material platform with unique quantum properties. The efficient light-matter interaction in atomic vapors has led to numerous seminal scientific achievements including accurate and precise…
Many classical and learning-based optical flow methods rely on hierarchical concepts to improve both accuracy and robustness. However, one of the currently most successful approaches -- RAFT -- hardly exploits such concepts. In this work,…
At present, object recognition studies are mostly conducted in a closed lab setting with classes in test phase typically in training phase. However, real-world problem is far more challenging because: i) new classes unseen in the training…
Feature Transformation (FT) crafts new features from original ones via mathematical operations to enhance dataset expressiveness for downstream models. However, existing FT methods exhibit critical limitations: discrete search struggles…
Due to its amazing three-dimensional effects, holography is a very motivating, yet very demanding subject for physics classes at the upper level in school. For this reason an instruction unit on holography that supplement holographic…